Our new Native AI engine lets you build, test and manage agents directly inside VoiceAIWrapper. Client portals, campaigns and billing are in the same place. If you’ve been away for a while, this is the biggest change: you no longer need to build your agent in a separate voice-provider platform first. Here’s what you can do now: 1. Turn a client’s website into an agent. Start with their business website. The new AI Agent Builder reads the content, asks a few questions and helps set up the agent’s knowledge and tools. Edit the setup and test it by voice or chat before launch. 2. Build more than an answering service. Create AI receptionists, outbound calling agents and website voice or chat agents. Configure appointment booking, SMS and call transfers around what your client actually needs. 3. Connect the work behind the conversation. Use GoHighLevel for CRM workflows, Google Calendar or Cal.com for scheduling, and APIs and webhooks to connect automations through n8n, Make or Zapier. 4. Make it your agency’s service. Add your branding, give each client a separate portal, choose their access and charge through your own Stripe account. Build and deliver the service without stitching together separate agent-building and client-management platforms. Already using Vapi, Retell AI or ElevenLabs? Keep your setup. BYOK is still available alongside Native. Phone services and connected tools still need their relevant accounts. Native removes the need for a separate voice AI provider, not those connections. Watch the Native AI + Agent Builder update: https://youtu.be/aDqtLYrH5nU See the full platform demo: https://youtu.be/qr3uTWGWwwg What’s one client use case you’d like to build with Native? Drop it below.

Most members who are stuck on "what do I lead with" are leading with something too big. Outbound campaigns, lead scoring, multi-step workflows. All of it works, but it takes a discovery call, a demo, and a follow-up before the client understands what they're buying. A white label AI receptionist doesn't need any of that. A plumber, a dental office, a law firm already knows what a missed call costs them. You're not selling a concept, you're selling the phone getting answered. → Pick one vertical you already have clients in. Don't do "local businesses" as a category — do dentists, or HVAC, or med spas. → Build one agent, one script, one voice. Reuse it across every client in that vertical. The second sale takes a fraction of the time of the first. → Put it on your domain with your logo and your product name. The client sees your brand, not Vapi's or Retell's. → Price it as a monthly service, not a per-minute product. Clients pay into your Stripe, we take no revenue share and add no markup to voice minutes, so the margin story is yours to set. → Wire it to the CRM on day one. GoHighLevel, HubSpot, Make, n8n — a call that doesn't leave a record in the client's system is a call they can't see the value of. Setup from API key to a branded portal runs about 60 minutes once you've done it once. The receptionist is the door, not the whole house. Once it's running and the client trusts it, outbound and reactivation campaigns become an easy upsell on an account that already works. Question for the room: which vertical are you selling the receptionist into, and what are you charging monthly? Drop it below - the pricing spread in here is the most useful thing we share.

GoHighLevel AI calling is easier to plan when you separate client access, calendar booking and contact workflows. If you're adding external voice agents to a client's GoHighLevel account, this walkthrough shows where each piece connects through VoiceAIWrapper. Watch it here: https://youtu.be/93g1wp_oovk Start with one client subaccount: 1. Connect your voice provider in VoiceAIWrapper so its agents are available for the integration. 2. Add the client's dashboard using the user-specific embed URL and GoHighLevel Custom Menu Links. Assign access to the intended subaccount. 3. Create calendar availability and booking tools for that same client. The dashboard embed and calendar connection are separate steps. 4. Connect the integration and find VoiceAIWrapper under Apps in the GoHighLevel workflow builder for contact and calling actions. Then test one complete path: the intended contact enters the workflow, the call runs, and any appointment lands on the correct calendar. That is my suggested next step after the setup overview, not a completed test shown in the video. Keep the user-specific embed URL private. It contains a secret access token. The goal is a client who can use the service inside their existing subaccount, with access and booking configured for their business. A visible dashboard alone does not prove the workflow works. Official marketplace app: https://marketplace.gohighlevel.com/integration/6a902f5081bcd97acb8872ee/versions/6a902f5081bcd97acb8872ee Which part would be most useful for the next walkthrough: calendar booking, contact workflows, or client rebilling?

A website chatbot does not need to be a large software project. This video shows how to set up an AI chatbot for website visitors without writing code: https://youtu.be/NLcyjLZsnIM For agencies, the useful part is not the chatbot itself. It is the service you can build around it: - Train the bot on the client’s website content and common questions. - Use it to answer visitors before they submit a form or call. - Add qualification questions so the client receives better leads. - Review unanswered questions and improve the bot over time. - Package setup, testing, and monthly maintenance as a recurring service. The main lesson is simple: start with a narrow job. A bot that answers five important questions correctly is more useful than one that tries to handle every possible conversation. One caveat: no-code setup does not remove the work. You still need to check the source content, test the answers, define escalation rules, and make sure the client’s team knows what happens when the bot cannot help. If you were adding this to your agency offer, which type of business would you target first, and what question would you want the chatbot to handle?